@article{towardsversatileandefficientvisual,
  title = {Towards Versatile and Efficient Visual Knowledge Integration into Pre-trained Language Models with Cross-Modal Adapters},
  author = {Xinyun Zhang and Haochen Tan and Han Wu and Bei Yu},
  year = {2023},
  eprint = {2305.07358},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2305.07358v4},
}